Introducing Intel(R) MPI Benchmarks

Contents

Introducing Intel(R) MPI Benchmarks#

Intel(R) MPI Benchmarks performs a set of MPI performance measurements for point-to-point and global communication operations for a range of message sizes. Intel(R) MPI Benchmarks is developed using ANSI C plus standard MPI. It is distributed as an open source project to enable use of benchmarks across various cluster architectures and MPI implementations.

The generated benchmark data fully characterizes:

  • performance of a cluster system, including node performance, network latency, and throughput

  • efficiency of the MPI implementation used

Package Contents#

The Intel(R) MPI Benchmarks package consists of the following components:

IMB-MPI1 – benchmarks for MPI-1 functions.

Components for MPI-2 functionality:

  • IMB-EXT – one-sided communications benchmarks.

  • IMB-IO – input/output (I/O) benchmarks.

Components for MPI-3 functionality:

  • IMB-NBC – benchmarks for non-blocking collective (NBC) operations.

  • IMB-RMA – one-sided communications benchmarks. These benchmarks measure the Remote Memory Access (RMA) functionality introduced in the MPI-3 standard.

  • IMB-MT – benchmarks for MPI-1 functions running within multiple threads per rank.

Each component constitutes a separate executable file. You can run all of the supported benchmarks, or specify a single executable file in the command line to get results for a specific subset of benchmarks.

If you do not have the MPI-2 or MPI-3 extensions available, you can install and use IMB-MPI1 that uses only standard MPI-1 functions.